Profile Job Results
Jobs
jpelwdnvg
Results Ready
Name
convnext_tiny
Target Device
- Samsung Galaxy S26
- Android 16
- Snapdragon® 8 Elite Gen 5 for Galaxy | SM8850-AD
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: float32[1, 224, 224, 3]Completion Time
7/4/2026, 7:19:10 PM
Versions
- LiteRT: 1.4.4
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 16 (BP4A.251205.006)
- AI Hub: aihub-2026.06.19.2
Estimated Inference Time
1.34 ms
Estimated Peak Memory Usage
0 ‑ 74 MB
Compute Units
NPU
328
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.35 s | 154‑162 MB |
Subsequent App Load | 137 ms | 58‑133 MB |
Inference | 1.34 ms | 0‑74 MB |
| Lite RT | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device